#521 · Primary category： Computer Vision
FreeAnchor
FreeAnchor: Learning to Match Anchors for Visual Object Detection (NeurIPS 2019)
Project last updated：11/30/19
GitHub Stars
668
Forks
108
Contributors
1
License
MIT
Why we included this project
FreeAnchor is the reference implementation of the NeurIPS 2019 paper of the same name, which proposes learning how to match anchors to ground-truth objects instead of relying on fixed IoU thresholds. That makes it a natural starting point for researchers reproducing the paper's COCO results or anyone curious about how one-stage detectors decide which anchor belongs to which object. The code sits on top of maskrcnn-benchmark and includes configs for ResNet and ResNeXt backbones, pretrained weights, and multi-scale testing. One practical note: the method is also available in mmdetection, so teams already using that framework will probably find it easier to work with it there than to maintain this standalone repo.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)